summaryrefslogtreecommitdiff
path: root/mm/migrate.c
diff options
context:
space:
mode:
authorAndrea Arcangeli <aarcange@redhat.com>2018-10-26 15:10:40 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-10-26 16:38:15 -0700
commit7066f0f933a1fd707bb38781866657769cff7efc (patch)
tree79fb72354932977e88ec6dbeb4adbc63403cad08 /mm/migrate.c
parentd7c3393413fe7e7dc54498ea200ea94742d61e18 (diff)
mm: thp: fix mmu_notifier in migrate_misplaced_transhuge_page()
change_huge_pmd() after arming the numa/protnone pmd doesn't flush the TLB right away. do_huge_pmd_numa_page() flushes the TLB before calling migrate_misplaced_transhuge_page(). By the time do_huge_pmd_numa_page() runs some CPU could still access the page through the TLB. change_huge_pmd() before arming the numa/protnone transhuge pmd calls mmu_notifier_invalidate_range_start(). So there's no need of mmu_notifier_invalidate_range_start()/mmu_notifier_invalidate_range_only_end() sequence in migrate_misplaced_transhuge_page() too, because by the time migrate_misplaced_transhuge_page() runs, the pmd mapping has already been invalidated in the secondary MMUs. It has to or if a secondary MMU can still write to the page, the migrate_page_copy() would lose data. However an explicit mmu_notifier_invalidate_range() is needed before migrate_misplaced_transhuge_page() starts copying the data of the transhuge page or the below can happen for MMU notifier users sharing the primary MMU pagetables and only implementing ->invalidate_range: CPU0 CPU1 GPU sharing linux pagetables using only ->invalidate_range ----------- ------------ --------- GPU secondary MMU writes to the page mapped by the transhuge pmd change_pmd_range() mmu..._range_start() ->invalidate_range_start() noop change_huge_pmd() set_pmd_at(numa/protnone) pmd_unlock() do_huge_pmd_numa_page() CPU TLB flush globally (1) CPU cannot write to page migrate_misplaced_transhuge_page() GPU writes to the page... migrate_page_copy() ...GPU stops writing to the page CPU TLB flush (2) mmu..._range_end() (3) ->invalidate_range_stop() noop ->invalidate_range() GPU secondary MMU is invalidated and cannot write to the page anymore (too late) Just like we need a CPU TLB flush (1) because the TLB flush (2) arrives too late, we also need a mmu_notifier_invalidate_range() before calling migrate_misplaced_transhuge_page(), because the ->invalidate_range() in (3) also arrives too late. This requirement is the result of the lazy optimization in change_huge_pmd() that releases the pmd_lock without first flushing the TLB and without first calling mmu_notifier_invalidate_range(). Even converting the removed mmu_notifier_invalidate_range_only_end() into a mmu_notifier_invalidate_range_end() would not have been enough to fix this, because it run after migrate_page_copy(). After the hugepage data copy is done migrate_misplaced_transhuge_page() can proceed and call set_pmd_at without having to flush the TLB nor any secondary MMUs because the secondary MMU invalidate, just like the CPU TLB flush, has to happen before the migrate_page_copy() is called or it would be a bug in the first place (and it was for drivers using ->invalidate_range()). KVM is unaffected because it doesn't implement ->invalidate_range(). The standard PAGE_SIZEd migrate_misplaced_page is less accelerated and uses the generic migrate_pages which transitions the pte from numa/protnone to a migration entry in try_to_unmap_one() and flushes TLBs and all mmu notifiers there before copying the page. Link: http://lkml.kernel.org/r/20181013002430.698-3-aarcange@redhat.com Signed-off-by: Andrea Arcangeli <aarcange@redhat.com> Acked-by: Mel Gorman <mgorman@suse.de> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Cc: Jerome Glisse <jglisse@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/migrate.c')
-rw-r--r--mm/migrate.c19
1 files changed, 6 insertions, 13 deletions
diff --git a/mm/migrate.c b/mm/migrate.c
index 93d9a1e25aad..905c2264c788 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1975,8 +1975,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
int isolated = 0;
struct page *new_page = NULL;
int page_lru = page_is_file_cache(page);
- unsigned long mmun_start = address & HPAGE_PMD_MASK;
- unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE;
+ unsigned long start = address & HPAGE_PMD_MASK;
+ unsigned long end = start + HPAGE_PMD_SIZE;
new_page = alloc_pages_node(node,
(GFP_TRANSHUGE_LIGHT | __GFP_THISNODE),
@@ -2003,11 +2003,9 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
WARN_ON(PageLRU(new_page));
/* Recheck the target PMD */
- mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
ptl = pmd_lock(mm, pmd);
if (unlikely(!pmd_same(*pmd, entry) || !page_ref_freeze(page, 2))) {
spin_unlock(ptl);
- mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
/* Reverse changes made by migrate_page_copy() */
if (TestClearPageActive(new_page))
@@ -2038,8 +2036,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
* new page and page_add_new_anon_rmap guarantee the copy is
* visible before the pagetable update.
*/
- flush_cache_range(vma, mmun_start, mmun_end);
- page_add_anon_rmap(new_page, vma, mmun_start, true);
+ flush_cache_range(vma, start, end);
+ page_add_anon_rmap(new_page, vma, start, true);
/*
* At this point the pmd is numa/protnone (i.e. non present) and the TLB
* has already been flushed globally. So no TLB can be currently
@@ -2051,7 +2049,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
* MADV_DONTNEED won't wait on the pmd lock and it'll skip clearing this
* pmd.
*/
- set_pmd_at(mm, mmun_start, pmd, entry);
+ set_pmd_at(mm, start, pmd, entry);
update_mmu_cache_pmd(vma, address, &entry);
page_ref_unfreeze(page, 2);
@@ -2060,11 +2058,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
set_page_owner_migrate_reason(new_page, MR_NUMA_MISPLACED);
spin_unlock(ptl);
- /*
- * No need to double call mmu_notifier->invalidate_range() callback as
- * the above pmdp_huge_clear_flush_notify() did already call it.
- */
- mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
/* Take an "isolate" reference and put new page on the LRU. */
get_page(new_page);
@@ -2088,7 +2081,7 @@ out_fail:
ptl = pmd_lock(mm, pmd);
if (pmd_same(*pmd, entry)) {
entry = pmd_modify(entry, vma->vm_page_prot);
- set_pmd_at(mm, mmun_start, pmd, entry);
+ set_pmd_at(mm, start, pmd, entry);
update_mmu_cache_pmd(vma, address, &entry);
}
spin_unlock(ptl);